TY - GEN
T1 - A framework of static hand shape recognition system
AU - Zhang, Shufen
AU - Ma, Liling
AU - Wang, Junzheng
PY - 2013
Y1 - 2013
N2 - The Shape Context is not rotation-invariant as the gesture features, and the computational cost is expensive. In this paper, a novel method named as Shape Context based on the key points is proposed. The contour points with larger curvature are looked as key points, and the direction of the key point is described as x-axis direction, then Shape Context feature histogram is calculated. These make features translation, scaling and rotation invariant and reduce the time complexity. Meanwhile, the experiments show the method is effective and efficiency in the real-time system.
AB - The Shape Context is not rotation-invariant as the gesture features, and the computational cost is expensive. In this paper, a novel method named as Shape Context based on the key points is proposed. The contour points with larger curvature are looked as key points, and the direction of the key point is described as x-axis direction, then Shape Context feature histogram is calculated. These make features translation, scaling and rotation invariant and reduce the time complexity. Meanwhile, the experiments show the method is effective and efficiency in the real-time system.
KW - Hand gesture
KW - Invariant
KW - Recognition
KW - Shape context
UR - http://www.scopus.com/inward/record.url?scp=84869464444&partnerID=8YFLogxK
U2 - 10.1007/978-3-642-34531-9_61
DO - 10.1007/978-3-642-34531-9_61
M3 - Conference contribution
AN - SCOPUS:84869464444
SN - 9783642345302
T3 - Lecture Notes in Electrical Engineering
SP - 577
EP - 585
BT - Proceedings of the 2012 International Conference on Information Technology and Software Engineering - Software Engineering and Digital Media Technology
T2 - 2012 International Conference on Information Technology and Software Engineering, ITSE 2012
Y2 - 8 December 2012 through 10 December 2012
ER -